The patch titled
readahead: state based method - routines
has been added to the -mm tree. Its filename is
readahead-state-based-method-routines.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: readahead: state based method - routines
From: Wu Fengguang <wfg@xxxxxxxxxxxxxxxx>
Extend struct file_ra_state to support the adaptive read-ahead logic.
Also define some helpers for it.
Signed-off-by: Wu Fengguang <wfg@xxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
include/linux/fs.h | 57 ++++++++++--
mm/readahead.c | 189 ++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 234 insertions(+), 12 deletions(-)
diff -puN include/linux/fs.h~readahead-state-based-method-routines include/linux/fs.h
--- 25/include/linux/fs.h~readahead-state-based-method-routines Fri May 26 13:34:10 2006
+++ 25-akpm/include/linux/fs.h Fri May 26 13:34:10 2006
@@ -613,21 +613,58 @@ struct fown_struct {
/*
* Track a single file's readahead state
+ *
+ * Diagram for the adaptive readahead logic:
+ *
+ * |--------- old chunk ------->|-------------- new chunk -------------->|
+ * +----------------------------+----------------------------------------+
+ * | # | # |
+ * +----------------------------+----------------------------------------+
+ * ^ ^ ^ ^
+ * file_ra_state.la_index .ra_index .lookahead_index .readahead_index
+ *
+ * Deduced sizes:
+ * |----------- readahead size ------------>|
+ * +----------------------------+----------------------------------------+
+ * | # | # |
+ * +----------------------------+----------------------------------------+
+ * |------- invoke interval ------>|-- lookahead size -->|
*/
struct file_ra_state {
- unsigned long start; /* Current window */
- unsigned long size;
- unsigned long flags; /* ra flags RA_FLAG_xxx*/
- unsigned long cache_hit; /* cache hit count*/
- unsigned long prev_page; /* Cache last read() position */
- unsigned long ahead_start; /* Ahead window */
- unsigned long ahead_size;
- unsigned long ra_pages; /* Maximum readahead window */
- unsigned long mmap_hit; /* Cache hit stat for mmap accesses */
- unsigned long mmap_miss; /* Cache miss stat for mmap accesses */
+ union {
+ struct { /* conventional read-ahead */
+ unsigned long start; /* Current window */
+ unsigned long size;
+ unsigned long ahead_start; /* Ahead window */
+ unsigned long ahead_size;
+ unsigned long cache_hit; /* cache hit count */
+ };
+#ifdef CONFIG_ADAPTIVE_READAHEAD
+ struct { /* adaptive read-ahead */
+ pgoff_t la_index;
+ pgoff_t ra_index;
+ pgoff_t lookahead_index;
+ pgoff_t readahead_index;
+ unsigned long age;
+ uint64_t cache_hits;
+ };
+#endif
+ };
+
+ /* mmap read-around */
+ unsigned long mmap_hit; /* Cache hit stat for mmap accesses */
+ unsigned long mmap_miss; /* Cache miss stat for mmap accesses */
+
+ /* common ones */
+ unsigned long flags; /* ra flags RA_FLAG_xxx*/
+ unsigned long prev_page; /* Cache last read() position */
+ unsigned long ra_pages; /* Maximum readahead window */
};
#define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */
#define RA_FLAG_INCACHE 0x02 /* file is already in cache */
+#define RA_FLAG_MMAP (1UL<<31) /* mmaped page access */
+#define RA_FLAG_NO_LOOKAHEAD (1UL<<30) /* disable look-ahead */
+#define RA_FLAG_EOF (1UL<<29) /* readahead hits EOF */
struct file {
/*
diff -puN mm/readahead.c~readahead-state-based-method-routines mm/readahead.c
--- 25/mm/readahead.c~readahead-state-based-method-routines Fri May 26 13:34:10 2006
+++ 25-akpm/mm/readahead.c Fri May 26 13:34:10 2006
@@ -832,6 +832,191 @@ static unsigned long node_readahead_agin
}
/*
+ * Some helpers for querying/building a read-ahead request.
+ *
+ * Diagram for some variable names used frequently:
+ *
+ * |<------- la_size ------>|
+ * +-----------------------------------------+
+ * | # |
+ * +-----------------------------------------+
+ * ra_index -->|<---------------- ra_size -------------->|
+ *
+ */
+
+static enum ra_class ra_class_new(struct file_ra_state *ra)
+{
+ return ra->flags & RA_CLASS_MASK;
+}
+
+static inline enum ra_class ra_class_old(struct file_ra_state *ra)
+{
+ return (ra->flags >> RA_CLASS_SHIFT) & RA_CLASS_MASK;
+}
+
+static unsigned long ra_readahead_size(struct file_ra_state *ra)
+{
+ return ra->readahead_index - ra->ra_index;
+}
+
+static unsigned long ra_lookahead_size(struct file_ra_state *ra)
+{
+ return ra->readahead_index - ra->lookahead_index;
+}
+
+static unsigned long ra_invoke_interval(struct file_ra_state *ra)
+{
+ return ra->lookahead_index - ra->la_index;
+}
+
+/*
+ * The 64bit cache_hits stores three accumulated values and a counter value.
+ * MSB LSB
+ * 3333333333333333 : 2222222222222222 : 1111111111111111 : 0000000000000000
+ */
+static int ra_cache_hit(struct file_ra_state *ra, int nr)
+{
+ return (ra->cache_hits >> (nr * 16)) & 0xFFFF;
+}
+
+/*
+ * Conceptual code:
+ * ra_cache_hit(ra, 1) += ra_cache_hit(ra, 0);
+ * ra_cache_hit(ra, 0) = 0;
+ */
+static void ra_addup_cache_hit(struct file_ra_state *ra)
+{
+ int n;
+
+ n = ra_cache_hit(ra, 0);
+ ra->cache_hits -= n;
+ n <<= 16;
+ ra->cache_hits += n;
+}
+
+/*
+ * The read-ahead is deemed success if cache-hit-rate >= 1/readahead_hit_rate.
+ */
+static int ra_cache_hit_ok(struct file_ra_state *ra)
+{
+ return ra_cache_hit(ra, 0) * readahead_hit_rate >=
+ (ra->lookahead_index - ra->la_index);
+}
+
+/*
+ * Check if @index falls in the @ra request.
+ */
+static int ra_has_index(struct file_ra_state *ra, pgoff_t index)
+{
+ if (index < ra->la_index || index >= ra->readahead_index)
+ return 0;
+
+ if (index >= ra->ra_index)
+ return 1;
+ else
+ return -1;
+}
+
+/*
+ * Which method is issuing this read-ahead?
+ */
+static void ra_set_class(struct file_ra_state *ra,
+ enum ra_class ra_class)
+{
+ unsigned long flags_mask;
+ unsigned long flags;
+ unsigned long old_ra_class;
+
+ flags_mask = ~(RA_CLASS_MASK | (RA_CLASS_MASK << RA_CLASS_SHIFT));
+ flags = ra->flags & flags_mask;
+
+ old_ra_class = ra_class_new(ra) << RA_CLASS_SHIFT;
+
+ ra->flags = flags | old_ra_class | ra_class;
+
+ ra_addup_cache_hit(ra);
+ if (ra_class != RA_CLASS_STATE)
+ ra->cache_hits <<= 16;
+
+ ra->age = node_readahead_aging();
+}
+
+/*
+ * Where is the old read-ahead and look-ahead?
+ */
+static void ra_set_index(struct file_ra_state *ra,
+ pgoff_t la_index, pgoff_t ra_index)
+{
+ ra->la_index = la_index;
+ ra->ra_index = ra_index;
+}
+
+/*
+ * Where is the new read-ahead and look-ahead?
+ */
+static void ra_set_size(struct file_ra_state *ra,
+ unsigned long ra_size, unsigned long la_size)
+{
+ /* Disable look-ahead for loopback file. */
+ if (unlikely(ra->flags & RA_FLAG_NO_LOOKAHEAD))
+ la_size = 0;
+
+ ra->readahead_index = ra->ra_index + ra_size;
+ ra->lookahead_index = ra->readahead_index - la_size;
+}
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static int ra_dispatch(struct file_ra_state *ra,
+ struct address_space *mapping, struct file *filp)
+{
+ enum ra_class ra_class = ra_class_new(ra);
+ unsigned long ra_size = ra_readahead_size(ra);
+ unsigned long la_size = ra_lookahead_size(ra);
+ pgoff_t eof_index = 1 + DIV_ROUND_UP(i_size_read(mapping->host),
+ PAGE_CACHE_SIZE);
+ int actual;
+
+ if (unlikely(ra->ra_index >= eof_index))
+ return 0;
+
+ /* Snap to EOF. */
+ if (ra->readahead_index + ra_size / 2 > eof_index) {
+ if (ra_class == RA_CLASS_CONTEXT_AGGRESSIVE &&
+ eof_index > ra->lookahead_index + 1)
+ la_size = eof_index - ra->lookahead_index;
+ else
+ la_size = 0;
+ ra_size = eof_index - ra->ra_index;
+ ra_set_size(ra, ra_size, la_size);
+ ra->flags |= RA_FLAG_EOF;
+ }
+
+ actual = __do_page_cache_readahead(mapping, filp,
+ ra->ra_index, ra_size, la_size);
+
+#ifdef CONFIG_DEBUG_READAHEAD
+ if (ra->flags & RA_FLAG_MMAP)
+ ra_account(ra, RA_EVENT_READAHEAD_MMAP, actual);
+ if (ra->readahead_index == eof_index)
+ ra_account(ra, RA_EVENT_READAHEAD_EOF, actual);
+ if (la_size)
+ ra_account(ra, RA_EVENT_LOOKAHEAD, la_size);
+ if (ra_size > actual)
+ ra_account(ra, RA_EVENT_IO_CACHE_HIT, ra_size - actual);
+ ra_account(ra, RA_EVENT_READAHEAD, actual);
+
+ dprintk("readahead-%s(ino=%lu, index=%lu, ra=%lu+%lu-%lu) = %d\n",
+ ra_class_name[ra_class],
+ mapping->host->i_ino, ra->la_index,
+ ra->ra_index, ra_size, la_size, actual);
+#endif /* CONFIG_DEBUG_READAHEAD */
+
+ return actual;
+}
+
+/*
* ra_min is mainly determined by the size of cache memory. Reasonable?
*
* Table of concrete numbers for 4KB page size:
@@ -903,10 +1088,10 @@ static void ra_account(struct file_ra_st
return;
if (e == RA_EVENT_READAHEAD_HIT && pages < 0) {
- c = (ra->flags >> RA_CLASS_SHIFT) & RA_CLASS_MASK;
+ c = ra_class_old(ra);
pages = -pages;
} else if (ra)
- c = ra->flags & RA_CLASS_MASK;
+ c = ra_class_new(ra);
else
c = RA_CLASS_NONE;
_
Patches currently in -mm which might be from wfg@xxxxxxxxxxxxxxxx are
readahead-kconfig-options.patch
radixtree-introduce-__radix_tree_lookup_parent.patch
radixtree-introduce-radix_tree_scan_hole.patch
mm-introduce-probe_pages.patch
mm-introduce-pg_readahead.patch
readahead-add-look-ahead-support-to-__do_page_cache_readahead.patch
readahead-delay-page-release-in-do_generic_mapping_read.patch
readahead-insert-cond_resched-calls.patch
readahead-minmax_ra_pages.patch
readahead-events-accounting.patch
readahead-rescue_pages.patch
readahead-sysctl-parameters.patch
readahead-min-max-sizes.patch
readahead-state-based-method-aging-accounting.patch
readahead-state-based-method-routines.patch
readahead-state-based-method.patch
readahead-context-based-method.patch
readahead-initial-method-guiding-sizes.patch
readahead-initial-method-thrashing-guard-size.patch
readahead-initial-method-expected-read-size.patch
readahead-initial-method-user-recommended-size.patch
readahead-initial-method.patch
readahead-backward-prefetching-method.patch
readahead-seeking-reads-method.patch
readahead-thrashing-recovery-method.patch
readahead-call-scheme.patch
readahead-laptop-mode.patch
readahead-loop-case.patch
readahead-nfsd-case.patch
readahead-turn-on-by-default.patch
readahead-debug-radix-tree-new-functions.patch
readahead-debug-traces-showing-accessed-file-names.patch
readahead-debug-traces-showing-read-patterns.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
